Pitfalls of Object Oriented Programming by SONY
•
27 gefällt mir•24,725 views
Pitfalls of Object Oriented Programming by SONY
Empfohlen
Weitere ähnliche Inhalte
Was ist angesagt?
Was ist angesagt? (20)
Andere mochten auch
Andere mochten auch (20)
Ähnlich wie Pitfalls of Object Oriented Programming by SONY
Ähnlich wie Pitfalls of Object Oriented Programming by SONY (20)
Kürzlich hochgeladen
Kürzlich hochgeladen (20)
Pitfalls of Object Oriented Programming by SONY
- 1. Sony Computer Entertainment Europe Research & Development Division Pitfalls of Object Oriented Programming Tony Albrecht – Technical Consultant Developer Services
- 2. What I will be covering • A quick look at Object Oriented (OO) programming • A common example • Optimisation of that example • Summary Slide 2
- 3. Object Oriented (OO) Programming • What is OO programming? – • a programming paradigm that uses "objects" – data structures consisting of datafields and methods together with their interactions – to design applications and computer programs. (Wikipedia) Includes features such as – – – – Data abstraction Encapsulation Polymorphism Inheritance Slide 3
- 4. What’s OOP for? • OO programming allows you to think about problems in terms of objects and their interactions. • Each object is (ideally) self contained – Contains its own code and data. – Defines an interface to its code and data. • Each object can be perceived as a „black box‟. Slide 4
- 5. Objects • If objects are self contained then they can be – Reused. – Maintained without side effects. – Used without understanding internal implementation/representation. • This is good, yes? Slide 5
- 6. Are Objects Good? • Well, yes • And no. • First some history. Slide 6
- 7. A Brief History of C++ C++ development started 1979 2009 Slide 7
- 8. A Brief History of C++ Named “C++” 1979 1983 2009 Slide 8
- 9. A Brief History of C++ First Commercial release 1979 1985 2009 Slide 9
- 10. A Brief History of C++ Release of v2.0 1979 1989 2009 Slide 10
- 11. A Brief History of C++ Added • multiple inheritance, • abstract classes, • static member functions, Release of v2.0 • const member functions • protected members. 1979 1989 2009 Slide 11
- 12. A Brief History of C++ Standardised 1979 1998 Slide 12 2009
- 13. A Brief History of C++ Updated 1979 2003 Slide 13 2009
- 14. A Brief History of C++ C++0x 1979 2009 Slide 14 ?
- 15. So what has changed since 1979? • Many more features have been added to C++ • CPUs have become much faster. • Transition to multiple cores • Memory has become faster. http://www.vintagecomputing.com Slide 15
- 16. CPU performance Slide 16 Computer architecture: a quantitative approach By John L. Hennessy, David A. Patterson, Andrea C. Arpaci-Dusseau
- 17. CPU/Memory performance Slide 17 Computer architecture: a quantitative approach By John L. Hennessy, David A. Patterson, Andrea C. Arpaci-Dusseau
- 18. What has changed since 1979? • One of the biggest changes is that memory access speeds are far slower (relatively) – 1980: RAM latency ~ 1 cycle – 2009: RAM latency ~ 400+ cycles • What can you do in 400 cycles? Slide 18
- 19. What has this to do with OO? • OO classes encapsulate code and data. • So, an instantiated object will generally contain all data associated with it. Slide 19
- 20. My Claim • With modern HW (particularly consoles), excessive encapsulation is BAD. • Data flow should be fundamental to your design (Data Oriented Design) Slide 20
- 21. Consider a simple OO Scene Tree • Base Object class – Contains general data • Node – Container class • Modifier – Updates transforms • Drawable/Cube – Renders objects Slide 21
- 22. Object • Each object – – – – Maintains bounding sphere for culling Has transform (local and world) Dirty flag (optimisation) Pointer to Parent Slide 22
- 23. Objects Class Definition Each square is 4 bytes Slide 23 Memory Layout
- 24. Nodes • Each Node is an object, plus – Has a container of other objects – Has a visibility flag. Slide 24
- 26. Consider the following code… • Update the world transform and world space bounding sphere for each object. Slide 26
- 27. Consider the following code… • Leaf nodes (objects) return transformed bounding spheres Slide 27
- 28. Consider the following code… • Leaf nodes (objects)this What‟s wrong with return transformed bounding code? spheres Slide 28
- 29. Consider the following code… • Leaf nodesm_Dirty=false thenreturn transformed If (objects) we get branch bounding misprediction which costs 23 or 24 spheres cycles. Slide 29
- 30. Consider the following code… • Leaf nodes (objects) return transformed of bounding Calculation12 cycles. bounding sphere spheresthe world takes only Slide 30
- 31. Consider the following code… • Leaf nodes (objects) return transformed bounding So using a dirty using oneis actually spheres flag here (in the case slower than not where it is false) Slide 31
- 32. Lets illustrate cache usage Main Memory Each cache line is 128 bytes Slide 32 L2 Cache
- 33. Cache usage Main Memory L2 Cache parentTransform is already in the cache (somewhere) Slide 33
- 34. Cache usage Main Memory Assume this is a 128byte boundary (start of cacheline) Slide 34 L2 Cache
- 35. Cache usage Main Memory L2 Cache Load m_Transform into cache Slide 35
- 36. Cache usage Main Memory L2 Cache m_WorldTransform is stored via cache (write-back) Slide 36
- 37. Cache usage Main Memory L2 Cache Next it loads m_Objects Slide 37
- 38. Cache usage Main Memory L2 Cache Then a pointer is pulled from somewhere else (Memory managed by std::vector) Slide 38
- 39. Cache usage Main Memory L2 Cache vtbl ptr loaded into Cache Slide 39
- 40. Cache usage Main Memory L2 Cache Look up virtual function Slide 40
- 41. Cache usage Main Memory L2 Cache Then branch to that code (load in instructions) Slide 41
- 42. Cache usage Main Memory L2 Cache New code checks dirty flag then sets world bounding sphere Slide 42
- 43. Cache usage Main Memory L2 Cache Node‟s World Bounding Sphere is then Expanded Slide 43
- 44. Cache usage Main Memory L2 Cache Then the next Object is processed Slide 44
- 45. Cache usage Main Memory L2 Cache First object costs at least 7 cache misses Slide 45
- 46. Cache usage Main Memory L2 Cache Subsequent objects cost at least 2 cache misses each Slide 46
- 47. The Test • 11,111 nodes/objects in a tree 5 levels deep • Every node being transformed • Hierarchical culling of tree • Render method is empty Slide 47
- 48. Performance This is the time taken just to traverse the tree! Slide 48
- 49. Why is it so slow? ~22ms Slide 49
- 51. Samples can be a little misleading at the source code level Slide 51
- 53. Stalls due to the load 2 instructions earlier Slide 53
- 54. Similarly with the matrix multiply Slide 54
- 55. Some rough calculations Branch Mispredictions: 50,421 @ 23 cycles each ~= 0.36ms Slide 55
- 56. Some rough calculations Branch Mispredictions: 50,421 @ 23 cycles each ~= 0.36ms L2 Cache misses: 36,345 @ 400 cycles each ~= 4.54ms Slide 56
- 57. • From Tuner, ~ 3 L2 cache misses per object – These cache misses are mostly sequential (more than 1 fetch from main memory can happen at once) – Code/cache miss/code/cache miss/code… Slide 57
- 58. Slow memory is the problem here • How can we fix it? • And still keep the same functionality and interface? Slide 58
- 59. The first step • Use homogenous, sequential sets of data Slide 59
- 61. Generating Contiguous Data • Use custom allocators – Minimal impact on existing code • Allocate contiguous – Nodes – Matrices – Bounding spheres Slide 61
- 62. Performance 19.6ms -> 12.9ms 35% faster just by moving things around in memory! Slide 62
- 63. What next? • Process data in order • Use implicit structure for hierarchy – Minimise to and fro from nodes. • Group logic to optimally use what is already in cache. • Remove regularly called virtuals. Slide 63
- 64. We start with a parent Node Hierarchy Node Slide 64
- 66. Hierarchy Node Node Node And they have a parent Slide 66
- 67. Hierarchy Node Node Node Node Node Node Node Node And they have children Slide 67 Node Node Node
- 68. Hierarchy Node Node Node Node Node Node Node Node And they all have parents Slide 68 Node Node Node
- 69. Hierarchy Node Node Node Node Node Node Node Node Node Node Node NodeNode Node Node A lot of this information can be inferred Slide 69 Node Node
- 70. Hierarchy Node Node Node Node Node Use a set of arrays, one per hierarchy level Node Node Node Slide 70 Node Node Node
- 71. Hierarchy Node Parent has 2 children :2 Node Node :4 :4 Node Children have 4 children Node Node Node Node Slide 71 Node Node Node
- 72. Hierarchy Ensure nodes and their data are contiguous in memory Node :2 Node Node :4 :4 Node Node Node Node Node Slide 72 Node Node Node
- 73. • Make the processing global rather than local – Pull the updates out of the objects. • No more virtuals – Easier to understand too – all code in one place. Slide 73
- 74. Need to change some things… • OO version – Update transform top down and expand WBS bottom up Slide 74
- 77. Node Node Node Node Node Node Node Update transform and world bounding sphere Slide 77 Node Node Node Node
- 78. Node Node Node Node Node Node Node Add bounding sphere of child Slide 78 Node Node Node Node
- 79. Node Node Node Node Node Node Node Update transform and world bounding sphere Slide 79 Node Node Node Node
- 80. Node Node Node Node Node Node Node Add bounding sphere of child Slide 80 Node Node Node Node
- 81. Node Node Node Node Node Node Node Update transform and world bounding sphere Slide 81 Node Node Node Node
- 82. Node Node Node Node Node Node Node Add bounding sphere of child Slide 82 Node Node Node Node
- 83. • Hierarchical bounding spheres pass info up • Transforms cascade down • Data use and code is „striped‟. – Processing is alternating Slide 83
- 84. Conversion to linear • To do this with a „flat‟ hierarchy, break it into 2 passes – Update the transforms and bounding spheres(from top down) – Expand bounding spheres (bottom up) Slide 84
- 85. Transform and BS updates Node :2 Node Node :4 :4 Node Node Node For each node at each level (top down) { multiply world transform by parent‟s transform wbs by world transform } Node Node Slide 85 Node Node Node
- 86. Update bounding sphere hierarchies Node :2 Node Node :4 :4 Node Node Node For each node at each level (bottom up) { add wbs to parent‟s } cull wbs against frustum } Node Node Slide 86 Node Node Node
- 87. Update Transform and Bounding Sphere How many children nodes to process Slide 87
- 88. Update Transform and Bounding Sphere For each child, update transform and bounding sphere Slide 88
- 89. Update Transform and Bounding Sphere Note the contiguous arrays Slide 89
- 90. So, what’s happening in the cache? Parent Unified L2 Cache Children node Children‟s data not needed Parent Data Childrens‟ Data Slide 90
- 91. Load parent and its transform Parent Unified L2 Cache Parent Data Childrens‟ Data Slide 91
- 92. Load child transform and set world transform Parent Unified L2 Cache Parent Data Childrens‟ Data Slide 92
- 93. Load child BS and set WBS Parent Unified L2 Cache Parent Data Childrens‟ Data Slide 93
- 94. Load child BS and set WBS Parent Next child is calculated with no extra cache misses ! Parent Data Childrens‟ Data Slide 94 Unified L2 Cache
- 95. Load child BS and set WBS Parent next 2 children incur 2 The cache misses in total Parent Data Childrens‟ Data Slide 95 Unified L2 Cache
- 96. Prefetching Parent Because all data is linear, we can predict what memory will be needed in ~400 cycles and prefetch Parent Data Childrens‟ Data Slide 96 Unified L2 Cache
- 97. • Tuner scans show about 1.7 cache misses per node. • But, these misses are much more frequent – Code/cache miss/cache miss/code – Less stalling Slide 97
- 98. Performance 19.6 -> 12.9 -> 4.8ms Slide 98
- 99. Prefetching • Data accesses are now predictable • Can use prefetch (dcbt) to warm the cache – Data streams can be tricky – Many reasons for stream termination – Easier to just use dcbt blindly • (look ahead x number of iterations) Slide 99
- 100. Prefetching example • Prefetch a predetermined number of iterations ahead • Ignore incorrect prefetches Slide 100
- 101. Performance 19.6 -> 12.9 -> 4.8 -> 3.3ms Slide 101
- 102. A Warning on Prefetching • This example makes very heavy use of the cache • This can affect other threads‟ use of the cache – Multiple threads with heavy cache use may thrash the cache Slide 102
- 103. The old scan ~22ms Slide 103
- 104. The new scan ~16.6ms Slide 104
- 106. Looking at the code (samples) Slide 106
- 107. Performance counters Branch mispredictions: 2,867 (cf. 47,000) L2 cache misses: 16,064 (cf 36,000) Slide 107
- 108. In Summary • Just reorganising data locations was a win • Data + code reorganisation= dramatic improvement. • + prefetching equals even more WIN. Slide 108
- 109. OO is not necessarily EVIL • Be careful not to design yourself into a corner • Consider data in your design – Can you decouple data from objects? – …code from objects? • Be aware of what the compiler and HW are doing Slide 109
- 110. Its all about the memory • Optimise for data first, then code. – Memory access is probably going to be your biggest bottleneck • Simplify systems – KISS – Easier to optimise, easier to parallelise Slide 110
- 111. Homogeneity • Keep code and data homogenous – Avoid introducing variations – Don‟t test for exceptions – sort by them. • Not everything needs to be an object – If you must have a pattern, then consider using Managers Slide 111
- 112. Remember • You are writing a GAME – You have control over the input data – Don‟t be afraid to preformat it – drastically if need be. • Design for specifics, not generics (generally). Slide 112
- 113. Data Oriented Design Delivers • • • • Better performance Better realisation of code optimisations Often simpler code More parallelisable code Slide 113
- 114. The END • Questions? Slide 114